morten-j/fine_tuned_ancient_semitic_BERT

README.md

@@ -0,0 +1,83 @@
+---
+tags:
+- generated_from_trainer
+metrics:
+- f1
+- precision
+- recall
+model-index:
+- name: fine_tuned_ancient_semitic_BERT
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# fine_tuned_ancient_semitic_BERT
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5170
+- F1: 0.2927
+- F5: 0.2847
+- Precision: 0.3158
+- Recall: 0.2727
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 20
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | F1     | F5     | Precision | Recall |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:---------:|:------:|
+| No log        | 1.0   | 65   | 0.3078          | 0.0    | 0.0    | 0.0       | 0.0    |
+| No log        | 2.0   | 130  | 0.3062          | 0.0    | 0.0    | 0.0       | 0.0    |
+| No log        | 3.0   | 195  | 0.3063          | 0.0    | 0.0    | 0.0       | 0.0    |
+| No log        | 4.0   | 260  | 0.3081          | 0.0    | 0.0    | 0.0       | 0.0    |
+| No log        | 5.0   | 325  | 0.2898          | 0.0    | 0.0    | 0.0       | 0.0    |
+| No log        | 6.0   | 390  | 0.3567          | 0.0    | 0.0    | 0.0       | 0.0    |
+| No log        | 7.0   | 455  | 0.3049          | 0.3529 | 0.3110 | 0.5455    | 0.2609 |
+| 0.2651        | 8.0   | 520  | 0.3008          | 0.4324 | 0.3957 | 0.5714    | 0.3478 |
+| 0.2651        | 9.0   | 585  | 0.3407          | 0.3784 | 0.3462 | 0.5       | 0.3043 |
+| 0.2651        | 10.0  | 650  | 0.3392          | 0.4    | 0.3571 | 0.5833    | 0.3043 |
+| 0.2651        | 11.0  | 715  | 0.2999          | 0.4444 | 0.4018 | 0.6154    | 0.3478 |
+| 0.2651        | 12.0  | 780  | 0.3231          | 0.5    | 0.4520 | 0.6923    | 0.3913 |
+| 0.2651        | 13.0  | 845  | 0.3056          | 0.5    | 0.4520 | 0.6923    | 0.3913 |
+| 0.2651        | 14.0  | 910  | 0.3097          | 0.5625 | 0.4820 | 1.0       | 0.3913 |
+| 0.2651        | 15.0  | 975  | 0.3168          | 0.6316 | 0.5846 | 0.8       | 0.5217 |
+| 0.1016        | 16.0  | 1040 | 0.3354          | 0.5882 | 0.5184 | 0.9091    | 0.4348 |
+| 0.1016        | 17.0  | 1105 | 0.3730          | 0.5    | 0.4284 | 0.8889    | 0.3478 |
+| 0.1016        | 18.0  | 1170 | 0.3749          | 0.5455 | 0.4741 | 0.9       | 0.3913 |
+| 0.1016        | 19.0  | 1235 | 0.3808          | 0.5161 | 0.4356 | 1.0       | 0.3478 |
+| 0.1016        | 20.0  | 1300 | 0.3620          | 0.5455 | 0.4741 | 0.9       | 0.3913 |
+
+
+### Framework versions
+
+- Transformers 4.38.1
+- Pytorch 2.2.1+cu121
+- Datasets 2.17.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "/home/morte/Downloads/trained_full_bert_model",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "NO_MATCH",
+    "1": "MATCH"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "MATCH": 1,
+    "NO_MATCH": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 52000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9b6d50390fd33828c8db61412be3d8c423d264ed79a69d541715f8da88aca65
+size 503939072

runs/Apr22_08-43-12_yoga/events.out.tfevents.1713768193.yoga.8613.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49ecf5b14c084521e42d3386d7aba29f9851b448ec76681e5ca0d7ed673910b8
+size 14811

runs/Apr22_08-43-12_yoga/events.out.tfevents.1713768381.yoga.8613.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99fa78865fe38da3a4a3a84773de648b6d1b5178fe7c7a9562865a62e4324562
+size 554

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,52 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff2eb0aeaad3e147061114db3405c55f951a3a9609e4871e09057396a3650875
+size 4920